Skip to main content
Glama
Vaquill-AI/vaquill-mcp

Vaquill-AI/vaquill-mcp

Official
by Vaquill-AI

Search State Session Laws

search_session_laws
Read-only

Search enacted US state session laws by keyword, exact phrase, citation, code section, or bill number to get ranked matches with the matching passage and snippet.

Instructions

Keyword search (BM25, not semantic) over the ENACTED text of US state session laws, best first, each with the passage that matched and a snippet. Send plain words, a quoted phrase (verbatim), a citation, a code section or a bill number. Words must match the act's own vocabulary: teeth cleaning will not find dental hygienist. Struck language is never searched. There is no 'no good match' flag, so read the snippet. An empty result is still charged.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_session_laws"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoLaws per page, 1 to 25. A page costs the same however many laws it holds, so a larger `limit` is cheaper per law.
queryYesPlain words, a quoted phrase (matched verbatim), a citation (`63-3004`), a code section or a bill number (`S.F.No. 1552`). Unquoted words are stemmed and matched as the legislature wrote them, so use the act's vocabulary. 2 to 300 characters.
offsetNoLaws to skip, for the next page: `offset` plus `limit` can reach at most the 60 best matches. Each page is a new search and is charged. Deeper than 60 is a 422, never charged: narrow the search with a filter instead.
seriesNoLimit to these numbering series (OR), as a result's series reports it; `general` is most states' ordinary chapter sequence. An unknown value is a 422, never charged.
sessionNoOne session, by the code `session.code` reports (`2025R`, `2025S1`). Case-sensitive. Applies to every kind of match, so a narrow session can leave fewer than `limit` laws on a page.
approvedToNoOnly laws approved on or before this date, `YYYY-MM-DD`, inclusive. An end before `approvedFrom` is a 422, never charged.
approvedFromNoOnly laws approved on or after this date, `YYYY-MM-DD`, inclusive; a real calendar date (`2025-02-30` is a 422). A law with no printed approval date never matches.
jurisdictionNoLimit to one jurisdiction: the 56 jurisdictions (the 50 states, `dc` and the territories `pr`, `gu`, `vi`, `as`, `mp`). Two-letter code, case-insensitive. Omit to search every jurisdiction we hold. `federal` and an unknown code are a 422, never charged.
instrumentTypeNoLimit to these kinds of measure, one or more (OR). One of `act`, `joint_resolution`, `concurrent_resolution`, `resolution`, `resolve`, `memorial`, `other`. Any other value is a 422, never charged.
Idempotency-KeyNoOptional, 16 to 255 visible ASCII characters (a UUIDv4 is ideal). A retry with the same key and request replays the original 2xx for 24 hours without charging again; the same key with a different request is rejected.
includeUnverifiedNoOpt in to results for laws we hold but do not serve for their text (`textStatus: withheld`). Default `false` leaves them out. With `true` they are returned and each carries `textReliability`, `reasonCode` and a `notice`; the text MAY show deleted or vetoed law as enacted. A law whose licence bars use is never returned.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only/non-destructive, and the description adds genuinely new behavior: struck language is never searched, there is no 'no good match' flag so the snippet must be read, and an empty result is still charged. Those are exactly the operational facts an agent needs before spending a call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five tight sentences, front-loaded with the search mode and corpus, then return shape, then query syntax, then caveats. Every sentence carries a distinct fact; nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter, billed search with an output schema, the description covers the parts structured data cannot: that matching is lexical, that struck text is excluded, that empty results cost money, and that snippets must be inspected. Nothing essential to calling it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns a bump by adding a concrete failure example (`teeth cleaning` will not find `dental hygienist`) that makes the query-vocabulary constraint actionable. It says little about the ten filter parameters, but those are fully documented in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource — keyword (BM25, explicitly not semantic) search over the ENACTED text of US state session laws — and states the return shape (laws best-first, each with the matching passage and a snippet). That scope plus the 'not semantic' qualifier lets an agent distinguish it from a semantic search sibling without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives strong how-to-use guidance: send plain words, a quoted phrase, a citation, a code section or a bill number, and expect the act's own vocabulary. It does not explicitly route to alternatives (e.g. the semantic `search` or `search_us_statutes`), so the when-not case is only implied by the 'not semantic' remark.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.